Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to changes in leadership or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouri
    -0.19
    hay
    -0.15
    hani
    -0.15
    wyn
    -0.14
    Sharper
    -0.14
    ataka
    -0.14
    .EventQueue
    -0.14
    иком
    -0.14
    rai
    -0.14
    Fil
    -0.13
    POSITIVE LOGITS
    .trace
    0.16
    interop
    0.16
    ceipt
    0.14
     trace
    0.14
    erule
    0.14
     invis
    0.14
    (trace
    0.14
    illion
    0.13
    igated
    0.13
    ure
    0.13
    Act Density 0.024%

    No Known Activations